Hacker News new | ask | show | jobs
by alboaie 472 days ago
Looks usefull. Could you explain how it works? you have to chain it after the call from other LLM ?
1 comments
lunarcave 472 days ago
Thanks.

We use a minimal schema[1] to prompt the LLM under the hood. We were inspired by BAML [2]. Then the output is wrangled with a converter and ajv [3].

[1] https://github.com/inferablehq/l1m/blob/main/api/src/schema....

[2] https://github.com/boundaryml/baml

[3] https://ajv.js.org

link